yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-15 04:01:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

add mps runtime (#223)

Browse Source
This commit is contained in:
Sebastian Raschka 2024-06-18 20:58:59 -05:00 committed by GitHub
parent fba205985d
commit 1ba1bb4c77
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
ch07/01_main-chapter-code/ch07.ipynb
View File

@ -1111,6 +1111,15 @@
"from functools import partial\n",
"\n",
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"\n",
"# If you have a Mac with Apple Silicon chip, you can uncomment the next lines of code\n",
"# to train the model on the Mac's GPU cores. However, as of this writing, this results in\n",
"# larger numerical deviations from the results shown in this chapter, because Apple Silicon\n",
"# support in PyTorch is still experimental\n",
"\n",
"# if torch.backends.mps.is_available():\n",
"# device = torch.device(\"mps\")\n",
"\n",
"print(\"Device:\", device)\n",
"\n",
"customized_collate_fn = partial(custom_collate_fn, device=device, allowed_max_length=1024)"
@ -1743,9 +1752,11 @@
"| Model | Device | Runtime for 2 Epochs |\n",
"|--------------------|-----------------------|----------------------|\n",
"| gpt2-medium (355M) | CPU (M3 MacBook Air) | 15.78 minutes |\n",
"| gpt2-small (124M) | GPU (M3 MacBook Air) | 10.77 minutes |\n",
"| gpt2-medium (355M) | GPU (L4) | 1.83 minutes |\n",
"| gpt2-medium (355M) | GPU (A100) | 0.86 minutes |\n",
"| gpt2-small (124M) | CPU (M3 MacBook Air) | 5.74 minutes |\n",
"| gpt2-small (124M) | GPU (M3 MacBook Air) | 3.73 minutes |\n",
"| gpt2-small (124M) | GPU (L4) | 0.69 minutes |\n",
"| gpt2-small (124M) | GPU (A100) | 0.39 minutes |\n",
"\n",